{"id":"https://openalex.org/W7126217762","doi":"https://doi.org/10.48550/arxiv.2601.21026","title":"Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes","display_name":"Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7126217762","doi":"https://doi.org/10.48550/arxiv.2601.21026"},"language":"en","primary_location":{"id":"pmh:doi:10.48550/arxiv.2601.21026","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048873755","display_name":"Louis Grenioux","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Grenioux, Louis","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123842180","display_name":"Maxence Noble","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noble, Maxence","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048873755"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.3050999939441681,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.3050999939441681,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2903999984264374,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.11479999870061874,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.5802000164985657},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.5666000247001648},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4999000132083893},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.44530001282691956},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.43790000677108765},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4101000130176544},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.3889999985694885},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.38769999146461487},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.37619999051094055}],"concepts":[{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5802000164985657},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5663999915122986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5188999772071838},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.46209999918937683},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.44530001282691956},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39079999923706055},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.3889999985694885},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.36390000581741333},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.33880001306533813},{"id":"https://openalex.org/C35304006","wikidata":"https://www.wikidata.org/wiki/Q5962","display_name":"Boltzmann constant","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3231000006198883},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3111000061035156},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30329999327659607},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C132725507","wikidata":"https://www.wikidata.org/wiki/Q39879","display_name":"Monte Carlo integration","level":5,"score":0.2637999951839447},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:doi:10.48550/arxiv.2601.21026","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:HAL:hal-05535535v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05535535","pdf_url":null,"source":{"id":"https://openalex.org/S4406922454","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2026","raw_type":"Preprints, Working Papers, ..."},{"id":"doi:10.48550/arxiv.2601.21026","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.21026","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2601.21026","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sampling":[0],"configurations":[1],"at":[2,213],"thermodynamic":[3],"equilibrium":[4],"is":[5,75,190],"a":[6,19,23,83,90,153,159,166,195],"central":[7],"challenge":[8],"in":[9,61,218],"statistical":[10],"physics.":[11],"Boltzmann":[12],"Generators":[13],"(BGs)":[14],"tackle":[15],"it":[16],"by":[17,81,150],"combining":[18],"generative":[20,100],"model":[21,57],"with":[22,165],"Monte":[24,71],"Carlo":[25,72],"(MC)":[26],"correction":[27],"step":[28],"to":[29,77,86,226,235],"obtain":[30],"asymptotically":[31],"unbiased":[32],"samples":[33],"from":[34,54,147,162,205],"an":[35,124],"unnormalized":[36],"target.":[37],"Most":[38],"current":[39],"BGs":[40,67],"use":[41],"classic":[42],"MC":[43],"mechanisms":[44],"such":[45],"as":[46],"importance":[47],"sampling,":[48],"which":[49,74,207],"both":[50],"require":[51],"tractable":[52],"likelihoods":[53],"the":[55,87,112,209,219,232],"backbone":[56],"and":[58,102,141,157],"scale":[59],"poorly":[60],"high-dimensional,":[62],"multi-modal":[63,132],"targets.":[64],"We":[65,122,192],"study":[66],"built":[68],"on":[69,130,200],"annealed":[70],"(aMC),":[73],"designed":[76],"overcome":[78],"these":[79],"limitations":[80],"bridging":[82],"simple":[84],"reference":[85],"target":[88],"through":[89],"sequence":[91],"of":[92,127,139],"intermediate":[93],"densities.":[94],"Diffusion":[95],"models":[96,101],"(DMs)":[97],"are":[98],"powerful":[99],"have":[103],"already":[104],"been":[105],"incorporated":[106],"into":[107],"aMC-based":[108],"recalibration":[109],"schemes":[110],"via":[111],"diffusion-induced":[113],"density":[114],"path,":[115],"making":[116],"them":[117],"appealing":[118],"backbones":[119],"for":[120],"aMC-BGs.":[121],"provide":[123],"empirical":[125],"meta-analysis":[126],"DM-based":[128],"aMC-BGs":[129],"controlled":[131],"Gaussian":[133],"mixtures":[134],"(varying":[135],"mode":[136],"separation,":[137],"number":[138],"modes,":[140],"dimension),":[142],"explicitly":[143],"disentangling":[144],"inference":[145],"effects":[146,149],"learning":[148],"comparing":[151],"(i)":[152],"perfectly":[154],"learned":[155],"DM":[156,160,237],"(ii)":[158],"trained":[161],"data.":[163],"Even":[164],"perfect":[167],"DM,":[168],"standard":[169],"integrations":[170],"using":[171],"only":[172],"first-order":[173,201,211],"stochastic":[174,210],"denoising":[175,181],"kernels":[176,182],"fail":[177],"systematically,":[178],"whereas":[179],"second-order":[180],"can":[183],"substantially":[184],"improve":[185],"performance":[186],"when":[187],"covariance":[188],"information":[189],"available.":[191],"further":[193],"propose":[194],"deterministic":[196],"aMC":[197],"integration":[198],"based":[199],"transport":[202],"maps":[203],"derived":[204],"DMs,":[206],"outperforms":[208],"variant":[212],"higher":[214],"computational":[215],"cost.":[216],"Finally,":[217],"learned-DM":[220],"setting,":[221],"all":[222],"DM-aMC":[223],"variants":[224],"struggle":[225],"produce":[227],"accurate":[228],"BGs;":[229],"we":[230],"trace":[231],"main":[233],"bottleneck":[234],"inaccurate":[236],"log-density":[238],"estimation.":[239]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-01T00:00:00"}